DeepSeek-V4.1-Flash-1017 GSQ+RCO GGUF: Run Under 12GB VRAM Locally

This video locally installs and explains DeepSeek-V4.1-Flash-1017 · GSQ-RCO GGUFs: Non-uniform GGUF quantizations of a 763B-parameter, 384-expert MoE, produced with GSQ and RCO. 📬Weekly AI Newsletter: https://fahdmirza.substack.com/ 🔥 Buy Me a Coffee to support the channel: https://ko-fi.com/fahdmirza #gsqrco #deepseeklocally PLEASE FOLLOW ME: ▶ LinkedIn: / fahdmirza ▶ YouTube: / @fahdmirza ▶ Blog: https://www.fahdmirza.com 0:00 Sufi dervish animation made locally 1:10 Running it with Strata on 12 GB VRAM 1:19 What is DeepSeek V4.1 Flash GSQ-RCO 2:19 Benchmarks 2:55 Full weight vs quantized weight 3:45 RCO and the size budget 4:45 GSQ and rounding options 5:42 How RCO and GSQ work together 6:35 Multilingual Test 7:32 Final thoughts RESOURCES: ▶ https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF All rights reserved © Fahd Mirza